© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 15-RESID-POST-AA · 2265 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
2265

INDEX

Explanations

the

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 NSURL

-0.07

谖

-0.07

nąć

-0.07

好事

-0.07

.phi

-0.07

ochrome

-0.07

 Mill

-0.07

.norm

-0.07

 nell

-0.06

ם

-0.06

POSITIVE LOGITS

onnen

0.07

_idxs

0.06

])))↵

0.06

经费

0.06

?>
↵

0.06

 },
↵
↵

0.06

İM

0.06

 tensions

0.06

 tested

0.06

番

0.06

Activations Density 0.082%

No Known Activations